Automated visual inspection and defect detection of large-scale silicon strip sensors
Bibliographic record
Abstract
Abstract For the Phase-II Upgrade of the ATLAS Detector, the Inner Detector will be replaced with the Inner Tracker (ITk), consisting of a pixel and a strip tracker. The 17,888 silicon strip detector modules comprising the ITk strip tracker will be assembled from silicon strip sensors and flexes with readout chips in a manual assembly process performed at 20 module assembly sites in a complex distribution chain, which requires quality control steps to be performed after each distribution and assembly step. Sensor quality control requires a visual inspection of the full sensor area (about 100 cm2) of each sensor to detect and log any defects (e.g. scratches, breakdown areas or chipped corners) or contamination. Since manual surveys of full sensor areas for several thousand sensors are both time-consuming and prone to errors, alternative methods were investigated to automate the process and improve its reliability. This paper presents a setup developed to take high-resolution images of full silicon strip sensors with high repeatability quickly and an algorithm developed for the automated detection of defects, built using functions and filters from popular open-source visual processing packages OpenCV and Scikit-image. Methods were developed both for small-scale high-resolution images and full-size sensor images with lower resolution — both are presented here.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".